Choice Within Limits: A Machine Learning Perspective on School Choice

View at publisher Summarise with VIRAT
Authors: Cammie Justus-Smith, Tzu‐Wei Wang, Georgia Heyward
Cited by: 0
References: 27

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This study examines factors shaping U.S. families’ enrollment in assigned public, public-of-choice (charter or magnet), and private schools, emphasizing how parental priorities operate within available opportunities. Using NHES:2019 data from families actively considering school options, we used a two-stage approach: Random Forest models identified key predictors, and multinomial logistic regression estimated interpretable associations. School cost, class size, and student body characteristics were strongly associated with private school enrollment, while academic performance and location were linked to public-of-choice selection. Geographic context and family structure also shaped enrollment patterns, highlighting how access, geography, and family resources structure participation in school choice systems.

Fields of Study & Subjects

School Choice and Performance Diverse Education Studies and Reforms Parental Involvement in Education

Publication details

Journal / source
Journal of School Choice
Pages
1–14
Publication date
31 March 2026
Language
EN